The lasso for high dimensional regression with a possible change point

Abstract

We consider a high dimensional regression model with a possible change point due to a covariate threshold and develop the lasso estimator of regression coefficients as well as the threshold parameter. Our lasso estimator not only selects covariates but also selects a model between linear and threshold regression models. Under a sparsity assumption, we derive non-asymptotic oracle inequalities for both the prediction risk and the l1-estimation loss for regression coefficients. Since the lasso estimator selects variables simultaneously, we show that oracle inequalities can be established without pretesting the existence of the threshold effect. Furthermore, we establish conditions under which the estimation error of the unknown threshold parameter can be bounded by a factor that is nearly n-1 even when the number of regressors can be much larger than the sample size n. We illustrate the usefulness of our proposed estimation method via Monte Carlo simulations and an application to real data.

Keywords: Lasso; Oracle inequalities; Sample splitting; Sparsity; Threshold models.

Figure 1

Mean prediction errors and mean $\mathcal{M}(\widehat{\mathit{\alpha }})$ (♦, τ=0.3; □, τ=0.4; ◯, τ=0.5; △, c=0): (a) M=100; (b) M=200; (c) M=400

Figure 2

Mean $l_1$‐errors for α and τ (♦, τ=0.3; □, τ=0.4; ◯, τ=0.5; △, c=0): (a) M=100; (b) M=200; (c) M=400